Electronic sensing systems and methods are disclosed. The electronic sensing system (ESS) receive an olfactory product and one or more smell characteristics of the olfactory product are detected and extracted by identifying a headspace of the olfactory product. A comparison of the extracted smell characteristics with one or more smell characteristics associated with a historic training data stored in a database is performed and a match between the extracted smell characteristics and the one or more smell characteristics associated with the historic training data is determined using machine learning technique(s). Further, the ESS generates a report for the olfactory product comprising at least one of type of the consumable, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, and classifies the olfactory product into one or more categories based on the report and/or the historic training data.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A processor implemented method, comprising: receiving, by an electronic sensing system ( 100 ), a olfactory product ( 302 ); detecting and extracting, using a sensing module ( 202 ) of the electronic sensing system ( 100 ), one or more smell characteristics of the olfactory product by identifying a headspace of the olfactory product ( 304 ); performing, by using a comparison module ( 204 ), a comparison of the one or more extracted smell characteristics of the olfactory product with smell characteristics associated with a historic training data stored in a database ( 306 ), wherein the database is dynamically updated with attributes associated with the one or more smell characteristics of the olfactory product; generating based on the comparison, by one or more neural network models, by using a report generation module ( 206 ), a report for the olfactory product comprising type of the olfactory product, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index ( 308 ), wherein the decaying index is computed based on a rate of decay of the olfactory product over a time period, wherein at least one of freshness characteristic and stale characteristic of the olfactory product is determined based on the decaying index, wherein an output of one or more neural network models is calculated with an expression of: labelling = activation e x i ∑ i = 1 n e x_i ; x i = w i t + b where ‘w’ is a weight and ‘b’ is bias towards each of the classes, and ‘e’ is exponential wherein total exponential is a calculation of probability, wherein the report is generated based on a minimum distance between the one or more extracted smell characteristics of the olfactory product and the smell characteristics associated with the historic training data stored in the database, wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising: receiving one or more olfactory products, extracting one or more smell characteristics of the one or more olfactory products, generating one or more reports pertaining to the one or more olfactory products and classifying the one or more olfactory products into one or more categories.
An electronic sensing system analyzes olfactory products by detecting and extracting smell characteristics from their headspace. The system compares these characteristics with stored data in a dynamically updated database containing historical smell profiles. A neural network model processes the comparison to generate a report identifying the product type, name, status, age, and a decaying index. The decaying index quantifies the product's degradation over time, determining freshness or staleness. The neural network uses an exponential activation function to classify the product based on weighted and biased inputs, calculating probabilities for each class. The report is generated by finding the closest match between the extracted smell characteristics and the stored data. The system is trained by processing multiple olfactory products, extracting their smell characteristics, generating reports, and categorizing them. This technology enables automated olfactory analysis for quality assessment, freshness monitoring, and product identification.
2. The processor implemented method of claim 1 , wherein the step of performing a comparison of the one or more extracted smell characteristics of the olfactory product with smell characteristics associated with a historic training data stored in a database comprises: analyzing the extracted smell characteristics of the olfactory product to obtain a set of normalized values and intensity values; performing a comparison of the set of normalized values and the intensity values with values associated with the historic training data stored in the database; and determining, using one or more neural network models, a match between the at least some of values from the set of normalized values and intensity values with the values with the historic training data stored in the database.
This invention relates to a method for analyzing and comparing olfactory product characteristics using machine learning techniques. The method addresses the challenge of accurately identifying and classifying smells by leveraging neural network models to match extracted smell characteristics with historic training data. The method involves extracting smell characteristics from an olfactory product, such as a fragrance or scent. These characteristics are then analyzed to generate normalized values and intensity values, which represent the smell's properties in a standardized format. The normalized and intensity values are compared against a database of historic training data, which contains previously recorded smell profiles. A neural network model processes this comparison to determine matches between the olfactory product's characteristics and the stored data. The neural network model evaluates the similarity between the extracted values and the historic data, identifying correlations or matches. This allows for precise identification or classification of the olfactory product based on its smell profile. The method enhances the accuracy of smell recognition by using machine learning to analyze and compare complex olfactory data, improving applications in fields like fragrance development, quality control, and sensory analysis.
3. The processor implemented method of claim 1 , further comprising classifying, using a classification module ( 208 ), the olfactory product into the one or more categories based on at least one of the generated report and the historic training data.
The invention relates to a processor-implemented method for analyzing and classifying olfactory products, such as fragrances or scents, using machine learning techniques. The method addresses the challenge of accurately categorizing olfactory products based on their chemical composition and sensory properties, which is difficult due to the subjective nature of scent perception and the complexity of chemical interactions. The method involves generating a report that includes data related to the olfactory product, such as its chemical composition, sensory attributes, and other relevant characteristics. This report is then used to classify the product into one or more predefined categories. The classification is performed by a classification module that leverages both the generated report and historic training data, which consists of previously analyzed olfactory products and their known classifications. The historic training data helps refine the classification process by providing a reference for comparing new products. The classification module may employ machine learning algorithms, such as neural networks or decision trees, to analyze the input data and determine the most appropriate category or categories for the olfactory product. The method ensures that the classification is objective and consistent, reducing reliance on human judgment and improving the accuracy of olfactory product categorization. This approach is particularly useful in industries such as perfumery, cosmetics, and food and beverage, where precise scent classification is essential for product development and quality control.
4. The processor implemented method of claim 1 , wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising: receiving one or more olfactory products; extracting one or more smell characteristics of the one or more olfactory products; generating one or more reports pertaining to the one or more olfactory products; and classifying the one or more olfactory products into the one or more categories.
This invention relates to an electronic sensing system for analyzing olfactory products, addressing the challenge of accurately identifying and categorizing smells. The system includes a processor-implemented method that trains the electronic sensing system using historic training data. The training process involves receiving one or more olfactory products, extracting their smell characteristics, generating reports about these products, and classifying them into predefined categories. The extracted smell characteristics may include chemical composition, intensity, or other sensory attributes. The generated reports document these characteristics and their classifications, enabling the system to learn and improve its recognition capabilities over time. Once trained, the system can receive new olfactory products, analyze their smell characteristics, and classify them based on the learned data. This method enhances the accuracy and reliability of electronic olfactory sensing, making it useful in applications such as quality control, environmental monitoring, or medical diagnostics. The training phase ensures the system can adapt to various olfactory profiles, improving its performance in real-world scenarios.
5. The processor implemented method of claim 1 , wherein the status of the olfactory product comprises at least one of consumable, and non-consumable.
The invention relates to a processor-implemented method for managing olfactory products, addressing the need to categorize and track the status of such products in a digital system. Olfactory products, which may include fragrances, scents, or other odor-emitting substances, are classified into distinct status categories to facilitate inventory management, usage tracking, and system operations. The method involves determining the status of an olfactory product, where the status includes at least one of "consumable" or "non-consumable." A consumable product is one that is depleted or used up over time, such as a fragrance that evaporates or a scent cartridge that empties. A non-consumable product, in contrast, does not deplete and may be reusable or have a fixed lifespan. The method may further involve processing this status information to trigger actions like replenishment alerts, usage monitoring, or system adjustments based on the product type. This classification helps optimize resource allocation, prevent shortages, and ensure proper maintenance of olfactory systems in applications like aromatherapy, environmental control, or sensory experiences. The method may integrate with broader systems for tracking product lifecycle, performance, or user preferences.
6. An electronic sensing system comprising: one or more processors ( 104 ); and one or more internal data storage devices ( 102 ) operatively coupled to the one or more processors ( 104 ) and storing instructions configured for execution by the one or more processors ( 104 ), the instructions comprises: a sensing module ( 202 ) that is configured to receive an olfactory product, and detect and extract one or more smell characteristics of the olfactory product by identifying a headspace of the olfactory product; a comparison module ( 204 ) configured to perform a comparison of the one or more extracted smell characteristics of the olfactory product with one or more smell characteristics associated with a historic training data stored in a database, wherein the database is dynamically updated with attributes associated with the one or more smell characteristics of the olfactory product; a report generation module ( 206 ) configured to generate, based on the comparison, using the one or more neural network models, a report for the olfactory product comprising at type of the olfactory product, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, wherein the decaying index is computed based on a rate of decay of the olfactory product over a time period, wherein at least one of freshness characteristic and stale characteristic of the olfactory product is determined based on the decaying index, wherein an output of one or more neural network models is calculated with an expression of: labelling = activation e x i ∑ i = 1 n e x_i ; x i = w i t + b where ‘w’ is a weight and ‘b’ is bias towards each of the classes, and ‘e’ is exponential wherein total exponential is a calculation of probability, wherein the report is generated based on a minimum distance between the one or more extracted smell characteristics of the olfactory product and the smell characteristics associated with the historic training data stored in the database, wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising: receiving one or more olfactory products, extracting one or more smell characteristics of the one or more olfactory products, generating one or more reports pertaining to the one or more olfactory products and classifying the one or more olfactory products into one or more categories.
The electronic sensing system is designed for analyzing olfactory products by detecting and extracting their smell characteristics. The system includes processors and internal data storage devices that execute instructions for olfactory analysis. A sensing module receives an olfactory product and identifies its headspace to detect and extract smell characteristics. A comparison module compares these extracted characteristics with historic training data stored in a dynamically updated database. The system uses neural network models to generate a report for the olfactory product, which includes its type, name, status, age, and a decaying index. The decaying index is computed based on the product's rate of decay over time, determining its freshness or stale characteristics. The neural network models use an exponential probability calculation to classify the product, with the report generated based on the minimum distance between the extracted smell characteristics and the historic data. Prior to operation, the system undergoes training by receiving olfactory products, extracting their smell characteristics, generating reports, and classifying them into categories. This system enables precise olfactory analysis and classification for quality assessment and monitoring.
7. The electronic sensing system of claim 6 , further comprising a classification module ( 208 ), that is configured to classify, using one or more classifiers, the olfactory product into the one or more categories based on the generated report and the historic training data.
This invention relates to an electronic sensing system designed to analyze olfactory products, such as fragrances or scents, and classify them into predefined categories. The system addresses the challenge of accurately identifying and categorizing olfactory products based on their chemical or sensory properties, which is difficult to achieve with traditional methods due to the complexity and subjectivity of scent analysis. The system includes a sensing module that detects and measures specific characteristics of the olfactory product, such as chemical composition or molecular structure. These measurements are processed to generate a detailed report that captures the key attributes of the product. Additionally, the system incorporates a classification module that uses one or more classifiers, such as machine learning models, to categorize the olfactory product based on the generated report and historic training data. The training data consists of previously analyzed samples and their corresponding classifications, enabling the system to improve its accuracy over time. This approach allows for automated and consistent classification of olfactory products, reducing reliance on human expertise and enhancing efficiency in industries like perfumery, cosmetics, and environmental monitoring.
8. The electronic sensing system of claim 6 , wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising: receiving one or more olfactory products; detecting and extracting one or more smell characteristics of the one or more olfactory products; generating one or more reports pertaining to the one or more olfactory products; and classifying the one or more olfactory products into the one or more categories.
The electronic sensing system is designed for analyzing olfactory products, such as fragrances or scents, by detecting and classifying their smell characteristics. The system addresses the challenge of accurately identifying and categorizing olfactory products, which is difficult due to the subjective and complex nature of scent perception. The system includes a training phase where it processes historic training data to improve its accuracy. During training, the system receives multiple olfactory products and detects their smell characteristics using sensors. It then generates reports on these products and classifies them into predefined categories based on their detected characteristics. This training process enables the system to recognize and categorize new olfactory products more effectively. The system's ability to learn from historic data enhances its reliability in identifying and classifying scents, making it useful in applications such as quality control, fragrance development, and environmental monitoring. The training phase ensures that the system can adapt to different types of olfactory products and improve its performance over time.
9. The electronic sensing system of claim 6 , wherein the status of the olfactory product comprises at least one of consumable, and non-consumable.
The invention relates to an electronic sensing system designed to detect and analyze olfactory products, such as fragrances or scents, to determine their status. The system addresses the challenge of accurately identifying whether an olfactory product is consumable (e.g., safe for use) or non-consumable (e.g., expired, contaminated, or otherwise unsuitable). The system includes a sensor module configured to detect chemical or physical properties of the olfactory product, such as molecular composition or concentration levels. A processing module interprets the sensor data to classify the product's status, ensuring users can reliably assess its condition. The system may also include a communication interface to transmit the status to external devices, such as smartphones or cloud servers, for further analysis or user notification. This technology is particularly useful in applications like perfume testing, air quality monitoring, or industrial scent production, where product integrity is critical. The system enhances safety and efficiency by automating the assessment of olfactory products, reducing the need for manual inspection or human judgment.
10. The electronic sensing system of claim 6 , wherein the one or more extracted smell characteristics of the olfactory product are compared with smell characteristics associated with a historic training data stored in the database by: analyzing the extracted smell characteristics of the olfactory product to obtain a set of normalized values and intensity values; performing a comparison of the set of normalized values and the intensity values with values associated with the historic training data stored in the database; and determining, using one or more neural network models, a match between the at least some of values from the set of normalized values and intensity values with the values with the historic training data stored in the database.
This invention relates to an electronic sensing system for analyzing olfactory products by comparing extracted smell characteristics with historic training data. The system addresses the challenge of accurately identifying and classifying smells using digital methods, which is difficult due to the subjective and complex nature of olfactory perception. The system extracts smell characteristics from an olfactory product, such as a fragrance or scent, and processes these characteristics to generate normalized values and intensity values. These values are then compared with pre-existing smell profiles stored in a database, which were derived from historic training data. The comparison involves analyzing the extracted values against the database entries to find matches. One or more neural network models are used to determine the similarity between the extracted smell characteristics and the stored profiles, enabling precise identification or classification of the olfactory product. The system enhances the accuracy of digital smell recognition by leveraging machine learning techniques to interpret and match complex olfactory data. This approach improves applications in quality control, fragrance development, and environmental monitoring where precise smell identification is critical.
11. One or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause; receiving, by an electronic sensing system, a olfactory product; detecting and extracting, one or more smell characteristics of the olfactory product by identifying a headspace of the olfactory product; performing, a comparison of the one or more extracted smell characteristics of the olfactory product with smell characteristics associated with a historic training data stored in a database, wherein the database is dynamically updated with attributes associated with the one or more smell characteristics of the olfactory product; generating based on the comparison, by one or more neural network models, a report for the olfactory product comprising type of the olfactory product, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, wherein the decaying index is computed based on a rate of decay of the olfactory product over a time period, wherein at least one of freshness characteristic and stale characteristic of the olfactory product is determined based on the decaying index, wherein an output of one or more neural network models is calculated with an expression of: labelling = activation e x i ∑ i = 1 n e x_i ; x i = w i t + b where ‘w’ is a weight and ‘b’ is bias towards each of the classes, and ‘e’ is exponential wherein total exponential is a calculation of probability, wherein the report is generated based on a minimum distance between the one or more extracted smell characteristics of the olfactory product and the smell characteristics associated with the historic training data stored in the database, wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising: receiving one or more olfactory products, extracting one or more smell characteristics of the one or more olfactory products, generating one or more reports pertaining to the one or more olfactory products and classifying the one or more olfactory products into one or more categories.
This invention relates to an electronic olfactory sensing system designed to analyze and classify olfactory products by detecting and extracting their smell characteristics. The system addresses the challenge of accurately identifying and assessing the quality, type, and condition of olfactory products, such as perfumes, foods, or other scented items, over time. The system receives an olfactory product and uses an electronic sensing system to detect and extract its smell characteristics by identifying the product's headspace—the volatile compounds released into the air. These extracted characteristics are then compared with historical training data stored in a dynamically updated database. The comparison is performed using one or more neural network models, which generate a report for the olfactory product. The report includes details such as the product's type, name, status, age, and a decaying index, which quantifies the product's rate of decay over time. The decaying index helps determine whether the product is fresh or stale. The neural network models use a probabilistic softmax function to classify the product, where the output is calculated using an exponential expression involving weights and biases. The system also includes a training phase, where the electronic sensing system is trained using historical data by receiving olfactory products, extracting their smell characteristics, generating reports, and classifying them into categories. The report generation is based on the minimum distance between the extracted smell characteristics and the historical data in the database. This invention enables automated, precise, and dynamic assessment of olfactory products, improving quality control and product management.
12. The one or more non-transitory machine readable information storage mediums of claim 11 , wherein the step of performing a comparison of the one or more extracted smell characteristics of the olfactory product with smell characteristics associated with a historic training data stored in a database comprises: analyzing the extracted smell characteristics of the olfactory product to obtain a set of normalized values and intensity values; performing a comparison of the set of normalized values and the intensity values with values associated with the historic training data stored in the database; and determining, using one or more neural network models, a match between the at least some of values from the set of normalized values and intensity values with the values with the historic training data stored in the database.
This invention relates to a system for analyzing and comparing olfactory product characteristics using machine learning. The technology addresses the challenge of accurately identifying and matching smell profiles of products by leveraging neural network models and historical training data. The system extracts smell characteristics from an olfactory product, such as scent composition and intensity, and processes these characteristics to generate normalized values and intensity values. These processed values are then compared against a database of historic training data, which contains pre-existing smell profiles. The comparison involves analyzing the extracted values to determine similarities or matches with the stored data. Neural network models are used to evaluate the comparison results, identifying correlations between the product's smell characteristics and the historic data. This enables precise identification or classification of the olfactory product based on its scent profile. The system enhances accuracy in smell analysis by normalizing and standardizing the extracted characteristics before comparison, ensuring reliable matching against the database. The use of neural networks further improves the system's ability to recognize complex scent patterns, making it suitable for applications in fragrance identification, quality control, and product authentication.
13. The one or more non-transitory machine readable information storage mediums of claim 11 , wherein the one or more instructions further cause classifying the olfactory product into the one or more categories based on at least one of the generated report and the historic training data.
This invention relates to a system for classifying olfactory products, such as fragrances or scents, using machine learning techniques. The system addresses the challenge of accurately categorizing olfactory products based on their sensory properties, which can be subjective and difficult to quantify. The invention involves analyzing sensory data from olfactory products and generating a report that includes key characteristics, such as scent profiles, intensity, and longevity. This report is then used to classify the product into predefined categories, such as floral, woody, or citrus, by comparing it to historic training data. The training data consists of previously classified olfactory products and their associated sensory profiles, enabling the system to learn and improve its classification accuracy over time. The classification process may also incorporate additional factors, such as user feedback or environmental conditions, to enhance precision. The system is implemented using one or more non-transitory machine-readable storage mediums containing instructions for executing the classification process. The invention aims to provide a standardized and automated method for categorizing olfactory products, improving consistency and efficiency in industries such as perfumery, cosmetics, and food and beverage.
14. The one or more non-transitory machine readable information storage mediums of claim 11 , wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising: receiving one or more olfactory products; extracting one or more smell characteristics of the one or more olfactory products; generating one or more reports pertaining to the one or more olfactory products; and classifying the one or more olfactory products into the one or more categories.
This invention relates to an electronic sensing system for analyzing olfactory products, addressing the challenge of accurately identifying and categorizing smells. The system includes one or more non-transitory machine-readable storage mediums containing instructions for training the electronic sensing system using historic training data. The training process involves receiving one or more olfactory products, extracting their smell characteristics, generating reports about these products, and classifying them into predefined categories. The extracted smell characteristics may include chemical composition, intensity, or other sensory attributes. The generated reports document these characteristics and their classifications, enabling the system to learn and improve its accuracy over time. This training phase ensures the system can reliably identify and categorize new olfactory products when they are later received for analysis. The system may also include a user interface for displaying the generated reports and classification results, allowing users to review and validate the system's performance. The overall goal is to enhance the precision and reliability of electronic smell detection and classification in various applications, such as quality control, environmental monitoring, or medical diagnostics.
15. The one or more non-transitory machine readable information storage mediums of claim 11 , wherein the status of the olfactory product comprises at least one of consumable, and non-consumable.
This invention relates to a system for managing olfactory products, such as fragrances or scents, stored in a machine-readable medium. The system addresses the challenge of tracking and categorizing olfactory products to ensure proper usage and inventory management. The invention involves a storage medium containing data that defines the status of an olfactory product, which can be classified as either consumable or non-consumable. Consumable products are those that can be used or dispensed, while non-consumable products may be samples, placeholders, or otherwise unavailable for use. The system allows for efficient tracking of product availability, ensuring that only valid, usable products are selected for dispensing. This classification helps prevent errors in inventory management and ensures that users receive the correct olfactory product. The storage medium may also include additional data, such as product identifiers, usage history, or expiration dates, to further enhance tracking and management. The invention improves the accuracy and reliability of olfactory product dispensing systems by clearly distinguishing between consumable and non-consumable items.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 11, 2017
February 15, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.